Do Deep Neural Networks Always Perform Better When Eating More Data?
Abstract
Data has now become a shortcoming of deep learning. Researchers in their own fields share the thinking that "deep neural networks might not always perform better when they eat more data," which still lacks experimental validation and a convincing guiding theory. Here to fill this lack, we design experiments from Identically Independent Distribution(IID) and Out of Distribution(OOD), which give powerful answers. For the purpose of guidance, based on the discussion of results, two theories are proposed: under IID condition, the amount of information determines the effectivity of each sample, the contribution of samples and difference between classes determine the amount of sample information and the amount of class information; under OOD condition, the cross-domain degree of samples determine the contributions, and the bias-fitting caused by irrelevant elements is a significant factor of cross-domain. The above theories provide guidance from the perspective of data, which can promote a wide range of practical applications of artificial intelligence.
Cite
@article{arxiv.2205.15187,
title = {Do Deep Neural Networks Always Perform Better When Eating More Data?},
author = {Jiachen Yang and Zhuo Zhang and Yicheng Gong and Shukun Ma and Xiaolan Guo and Yue Yang and Shuai Xiao and Jiabao Wen and Yang Li and Xinbo Gao and Wen Lu and Qinggang Meng},
journal= {arXiv preprint arXiv:2205.15187},
year = {2022}
}